Kovács, Attila D

Importance Clinical trials in cardiovascular medicine aim to deliver high-quality evidence with greater efficiency, including smaller sample sizes and shorter timelines. The selection of sensitive and reliable end points is central to this goal. Right ventricular (RV) structure and function play a critical role in many cardiovascular conditions; however, RV-specific parameters remain underused and inconsistently applied in interventional clinical trials. In this article, the current and emerging role of RV-focused imaging and hemodynamic parameters as end points in clinical trials are explored and a comprehensive framework for their development, validation, and broader implementation is proposed. Observations Across multiple disease domains, RV-focused parameters derived from echocardiography, cardiac magnetic resonance imaging, computed tomography, and right-sided heart catheterization demonstrate potential value in assessing the therapeutic effects of new medicines or devices across a wide range of conditions including heart failure, cardiomyopathies, valve diseases, pulmonary hypertension, and congenital heart conditions. However, their use is inconsistent, and feasibility challenges are common, particularly in multicenter clinical trial settings. Key limitations include variability in imaging acquisition, incomplete data capture, lack of standardized protocols, and insufficient validation linking short-term RV changes to long-term clinical outcomes. Emerging tools such as artificial intelligence may improve reproducibility and efficiency, while collaborative, multidisciplinary efforts are essential for advancing end-point development. Conclusions and Relevance RV-specific end points hold substantial promise for enhancing the sensitivity and mechanistic insight of clinical trials but remain inadequately integrated into current practice. Optimal end-point selection requires balancing clinical relevance, analytical validity, and operational feasibility, with consideration of disease-specific pathophysiology and trial design. Standardization of acquisition, validation of clinically meaningful changes, and centralized data analysis are important next steps. Broader adoption of robust RV metrics supported by technological innovation and cross-sector collaboration has the potential to improve trial efficiency, accelerate therapeutic development, and ultimately enhance patient outcomes.

Abstract Background Right ventricular (RV) systolic function is an independent predictor of outcome, but a robust automated method of quantitation is lacking. Purpose To develop and validate a deep learning model for quantifying RV systolic function from 2D echo clips and assess its prognostic value in various loading states and left-heart disease. Methods A deep learning convolutional neural network (CNN) was developed to quantitate RV systolic function using all available apical 4 chamber (A4C) views from 13,039 patients (61,187 A4C video clips) in a US institution. Videos were converted to frames of 256x256 grayscale pixels, with graphics, including the ECG, removed. The model used the S3D architecture, a 3D-CNN with many of the spatial and temporal convolutions separated. RV free wall longitudinal strain (RVFWLS) was used to define RV function: normal (≤-25%); mild (-20% to –24%); moderate (-15% to –19%) and severe RV dysfunction (0% to –14%). The AI-estimate was the average of multiple 32-frame segments for each clip identified as an A4C, including both standard and RV-focused variations. The model was validated in four distinct clinical cohorts from independent data sources: 1) 1365 patients referred to an external diagnostic echocardiography lab in a different US state; 2) 569 patients recruited prospectively with known or suspected pulmonary hypertension (PH); 3) 416 patients with moderate or greater tricuspid valve regurgitation (TR); 4) 872 patients imaged at an Eastern European University with left-sided cardiac diseases (valvular disease, cardiomyopathies, etc.), athletes, or healthy volunteers. Results Model output was strongly correlated with the presence of RV dysfunction by manual measurement [AUC 0.907 (95% CI: 0.888-0.926)] in the internal validation set. Results were similar in an external validation US cohort [N=1365; AUC 0.919 (95% CI: 0.899-0.939)]. When the model was applied to 569 patients with known or suspected PH, presence and severity of the AI measures of RV dysfunction were strongly associated with functional class, 6 min walk distance, NT-proBNP levels and right heart failure (p<0.001). The presence and severity of RV dysfunction (as categorized by the AI model) was strongly associated with all-cause mortality in patients with PH (Figure 1A) and in patients with significant TR (Figure 1B). The European cohort was a geographically and institutionally distinct cohort with a low prevalence of >mild TR (10.8%) or PH (6.4%). In this cohort the AI model predicted a reduced RVEF (< 45%) with an AUC of 0.864 (95% CI: 0.831-0.898) and associated with both all-cause mortality (Figure 2A) and a composite endpoint of heart failure hospitalization or death (Figure 2B). Conclusions A fully automated, AI-based assessment of RV systolic function, using 2D apical 4 chamber echo views alone, is highly feasible and can accurately categorize disease severity and predict outcome across a wide spectrum of cardiovascular conditions.Figure 1 Figure 2

Abstract Introduction Cardiopulmonary exercise testing (CPET) is an important diagnostic method to evaluate athletes and non-athletes, however we do not have widely accepted normal values for correct evaluation and interpretation in the young. Goals Our aim was to compare CPET parameters of young athletes and non-athletes and determine reference values. Methods Exercise tests were performed in young non-athletes, aged <18 years between 2011 to 2016 at Mayo Clinic. Athletes underwent detailed sports cardiology screening including CPET at Semmelweis University Heart and Vascular Center between 2016 and 2018. Individuals with cardiovascular disease were excluded. We created 2 subgroups in both sexes: 12–14 years (Group 1), 15–17 years (Group 2). Statistical analysis was performed using SAS with analysis of variance under the general linear model adjusting for age, body mass index and test effort based on peak respiratory exchange ratio (RER). Results A total of 212 athletes (92% male, 15.5±0.6ys) and 207 non-athletes (68% male, 15.0±0.7ys) were included in the analysis. In Group 1 boys, athletes have higher peak HR (200.0±9.2 vs 188.5±16.8 bpm, p<0.0001), HR reserve (117.1±14.5 vs 108.9±19.8 bpm p<0.05), VO2 max (53.7±6.6 vs 44.7±9.1 mL/kg/min p<0.0001), ventilation (VE) (120.3±25.0 vs 70.7±21.6 L/min p<0.0001) and RER (1.12±0.0 vs 1.07±0.08, p <.001) compared to controls. In Group 2 boys, there was no difference in peak HR and HR reserve, but athletes have higher VO2 max (57.2±4.7 vs 45.3±9.3 mL/kg/min, p<0.0001) and VE (150.7±23.7 vs 104.1±25.9 L/min, p<0.0001), similarly as Group 2 girls: VO2 max (46.3±3.6 vs 34.9±8.5 mL/kg/min p<0.0001), VE (118.7±12.5 vs 68.4±20.6 L/min, p<0.0001). In male athletes, peak HR (200.6±9.2 vs 196.5±7.4 bpm p<0.05) and HR recovery (34.2±9.8 vs 29.8±11.1 bpm p<0.05) decreases with age, while VO2 max (53.7±6.6 vs 57.2±4.7 mL/kg/min, p<0.001) and VE (120.3±24.9 vs 150.7±23.7 L/min, p<0.0001) increases. Lower cut-off values were determined in each group (Figure). Lower-cut off values Conclusion We created a unique Mayo-Semmelweis database of young athletes and non-athletes. As a result of intensive training, athletes show higher levels of CPET variables vs non-athletes. Our study provides CPET reference values in the pediatric age group, applying them could contribute to correct evaluation and interpretation of CPET, increasing its diagnostic potential.